A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations

TL;DR

This paper presents IfcLLM, a hybrid framework that combines relational and graph representations of IFC models with iterative LLM reasoning to enable accurate natural language querying for non-expert BIM users.

Contribution

The paper introduces a novel hybrid approach integrating relational and graph IFC representations with iterative LLM reasoning for improved natural language interaction.

Findings

First-attempt query accuracy of 93.3%-100%.

Fallback LLM recovers all failed queries.

Supports reproducible workflows with open-weight LLM.

Abstract

Building Information Modeling (BIM) is widely used in the Architecture, Engineering, and Construction (AEC) industry, but the complexity of Industry Foundation Classes (IFC) limits accessibility for non-expert users. To address this, we introduce IfcLLM, a hybrid framework for natural language interaction with IFC-based BIM models. It transforms IFC models into complementary representations: a relational representation for structured element properties and geometry, and a graph representation for topological relationships. These representations are integrated through iterative retry-and-refine LLM reasoning. We implement the framework using an open-weight LLM (GPT OSS 120B), supporting reproducible and deployment-oriented workflows. Evaluation on three IFC models with queries derived from 30 scenarios shows first-attempt accuracy of 93.3%-100%, with all failures recovered using a fallback LLM. The results show that combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data while supporting routine BIM analysis tasks.